Hugging Face's logo

mradermacher
/
gemma-2-27b-it-SkoleGPT-i1-GGUF

Transformers
GGUF
English
text-generation-inference
unsloth
gemma2
trl
sft
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
c2646e0
•
1 Parent(s): d8e9f28

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -36,18 +36,26 @@ more details, including on how to concatenate multi-part files.
36
 
37
  | Link | Type | Size/GB | Notes |
38
  |:-----|:-----|--------:|:------|
 
39
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-IQ1_M.gguf) | i1-IQ1_M | 6.8 | mostly desperate |
40
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 7.7 | |
 
 
41
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-IQ2_M.gguf) | i1-IQ2_M | 9.5 | |
42
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-Q2_K.gguf) | i1-Q2_K | 10.5 | IQ3_XXS probably better |
43
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 10.9 | lower quality |
 
 
44
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.3 | IQ3_XS probably better |
45
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-IQ3_M.gguf) | i1-IQ3_M | 12.6 | |
46
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.5 | IQ3_S probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 14.6 | IQ3_M probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 14.9 | |
 
49
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 15.8 | optimal size/speed/quality |
50
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 16.7 | fast, recommended |
 
 
51
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-Q6_K.gguf) | i1-Q6_K | 22.4 | practically like static Q6_K |
52
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
 
36
 
37
  | Link | Type | Size/GB | Notes |
38
  |:-----|:-----|--------:|:------|
39
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-IQ1_S.gguf) | i1-IQ1_S | 6.2 | for the desperate |
40
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-IQ1_M.gguf) | i1-IQ1_M | 6.8 | mostly desperate |
41
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 7.7 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-IQ2_XS.gguf) | i1-IQ2_XS | 8.5 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-IQ2_S.gguf) | i1-IQ2_S | 8.8 | |
44
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-IQ2_M.gguf) | i1-IQ2_M | 9.5 | |
45
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-Q2_K.gguf) | i1-Q2_K | 10.5 | IQ3_XXS probably better |
46
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 10.9 | lower quality |
47
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-IQ3_XS.gguf) | i1-IQ3_XS | 11.7 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-IQ3_S.gguf) | i1-IQ3_S | 12.3 | beats Q3_K* |
49
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.3 | IQ3_XS probably better |
50
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-IQ3_M.gguf) | i1-IQ3_M | 12.6 | |
51
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.5 | IQ3_S probably better |
52
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 14.6 | IQ3_M probably better |
53
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 14.9 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-Q4_0.gguf) | i1-Q4_0 | 15.8 | fast, low quality |
55
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 15.8 | optimal size/speed/quality |
56
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 16.7 | fast, recommended |
57
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-Q5_K_S.gguf) | i1-Q5_K_S | 19.0 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-Q5_K_M.gguf) | i1-Q5_K_M | 19.5 | |
59
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-27b-it-SkoleGPT-i1-GGUF/resolve/main/gemma-2-27b-it-SkoleGPT.i1-Q6_K.gguf) | i1-Q6_K | 22.4 | practically like static Q6_K |
60
 
61
  Here is a handy graph by ikawrakow comparing some lower-quality quant